Distribution Learning with Valid Outputs Beyond the Worst-Case

• Published in: arXiv.org
• Main Authors: Rittler, Nick, Chaudhuri, Kamalika
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 21.10.2024
• Subjects: Algorithms; Machine learning; Polynomials; Queries; Validity

Generative models at times produce "invalid" outputs, such as images with generation artifacts and unnatural sounds. Validity-constrained distribution learning attempts to address this problem by requiring that the learned distribution have a provably small fraction of its mass in invalid...